netflix ийн дата аналитик

1. Хэрэгтэй сангууд:

packages = c('tidyverse', 'kableExtra', 'plotly', 'lubridate', 'pacman')

for (p in packages){
  if (!require(p,character.only = T)){
    install.packages(p)
  }
  library(p,character.only = T)
}
p_load(tidyverse,lubridate,showtext)
showtext_auto()
font_add_google("Bebas Neue", "Bebas Neue")

2. Өгөгдөл уншиж авах:

df <- read_csv('dataset/netflix_titles.csv')

Rows: 8807 Columns: 12── Column specification ───────────────────────────────────────────────────────
Delimiter: ","
chr (11): show_id, type, title, director, cast, country, date_added, rating...
dbl  (1): release_year
ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

3. Өгөгдөл боловсруулалт

3.1 Өгөгдөл багсгалт

# Хэрэгцээгүй утгуудыг цэвэрлэх явц
df <- tibble::as_tibble(df) %>% 
  select(-c( description))

# дата шалтгалт
kable(df[1:10,]) %>%
  kable_styling(bootstrap_options = c("striped", "hover", "condensed")) %>%
  scroll_box(width = "100%", height = "500px")

show_id	type	title	director	cast	country	date_added	release_year	rating	duration	listed_in
s1	Movie	Dick Johnson Is Dead	Kirsten Johnson	NA	United States	September 25, 2021	2020	PG-13	90 min	Documentaries
s2	TV Show	Blood & Water	NA	Ama Qamata, Khosi Ngema, Gail Mabalane, Thabang Molaba, Dillon Windvogel, Natasha Thahane, Arno Greeff, Xolile Tshabalala, Getmore Sithole, Cindy Mahlangu, Ryle De Morny, Greteli Fincham, Sello Maake Ka-Ncube, Odwa Gwanya, Mekaila Mathys, Sandi Schultz, Duane Williams, Shamilla Miller, Patrick Mofokeng	South Africa	September 24, 2021	2021	TV-MA	2 Seasons	International TV Shows, TV Dramas, TV Mysteries
s3	TV Show	Ganglands	Julien Leclercq	Sami Bouajila, Tracy Gotoas, Samuel Jouy, Nabiha Akkari, Sofia Lesaffre, Salim Kechiouche, Noureddine Farihi, Geert Van Rampelberg, Bakary Diombera	NA	September 24, 2021	2021	TV-MA	1 Season	Crime TV Shows, International TV Shows, TV Action & Adventure
s4	TV Show	Jailbirds New Orleans	NA	NA	NA	September 24, 2021	2021	TV-MA	1 Season	Docuseries, Reality TV
s5	TV Show	Kota Factory	NA	Mayur More, Jitendra Kumar, Ranjan Raj, Alam Khan, Ahsaas Channa, Revathi Pillai, Urvi Singh, Arun Kumar	India	September 24, 2021	2021	TV-MA	2 Seasons	International TV Shows, Romantic TV Shows, TV Comedies
s6	TV Show	Midnight Mass	Mike Flanagan	Kate Siegel, Zach Gilford, Hamish Linklater, Henry Thomas, Kristin Lehman, Samantha Sloyan, Igby Rigney, Rahul Kohli, Annarah Cymone, Annabeth Gish, Alex Essoe, Rahul Abburi, Matt Biedel, Michael Trucco, Crystal Balint, Louis Oliver	NA	September 24, 2021	2021	TV-MA	1 Season	TV Dramas, TV Horror, TV Mysteries
s7	Movie	My Little Pony: A New Generation	Robert Cullen, José Luis Ucha	Vanessa Hudgens, Kimiko Glenn, James Marsden, Sofia Carson, Liza Koshy, Ken Jeong, Elizabeth Perkins, Jane Krakowski, Michael McKean, Phil LaMarr	NA	September 24, 2021	2021	PG	91 min	Children & Family Movies
s8	Movie	Sankofa	Haile Gerima	Kofi Ghanaba, Oyafunmike Ogunlano, Alexandra Duah, Nick Medley, Mutabaruka, Afemo Omilami, Reggie Carter, Mzuri	United States, Ghana, Burkina Faso, United Kingdom, Germany, Ethiopia	September 24, 2021	1993	TV-MA	125 min	Dramas, Independent Movies, International Movies
s9	TV Show	The Great British Baking Show	Andy Devonshire	Mel Giedroyc, Sue Perkins, Mary Berry, Paul Hollywood	United Kingdom	September 24, 2021	2021	TV-14	9 Seasons	British TV Shows, Reality TV
s10	Movie	The Starling	Theodore Melfi	Melissa McCarthy, Chris O'Dowd, Kevin Kline, Timothy Olyphant, Daveed Diggs, Skyler Gisondo, Laura Harrier, Rosalind Chao, Kimberly Quinn, Loretta Devine, Ravi Kapoor	United States	September 24, 2021	2021	PG-13	104 min	Comedies, Dramas

3.2 Хоосон утгуудыг цэвэрлэх, цэгцлэх

# Хоосон утгатай өгөгдлийг илрүүлэх
data.frame(var = c(colnames(df)), 
           missing = sapply(df, function(x) sum(is.na(x))), row.names = NULL) %>%
  mutate(missing = cell_spec(missing, "html", 
                             color = ifelse(missing > 0, 'red', 'black'))) %>% 
  rename(`Баганын нэр` = var, `Хоосон утгын тоо` = missing) %>%
  kable(format = "html", escape = F, align = c("l", "c")) %>%
  kable_styling(bootstrap_options = c("striped", "hover", "condensed"), full_width = F)

Баганын нэр	Хоосон утгын тоо
show_id	0
type	0
title	0
director	2634
cast	825
country	831
date_added	10
release_year	0
rating	4
duration	3
listed_in	0

# Мод олох функч
getmode <- function(v) {
   uniqv <- unique(v)
   uniqv[which.max(tabulate(match(v, uniqv)))]
}
df$rating[is.na(df$rating)] <- getmode(df$rating)

# давхардсан өгөгдөлүүдийг цэвэхлэх -> title, country, type болон release_year
df <- distinct(df, type, title, country, release_year, show_id, listed_in, .keep_all = T)

3.3 Он сарын порматын өөрчлөлт

# он сарын утгын порматын өөрчлөлт
df$date_added <- as.Date(df$date_added, format = "%B %d, %Y")

# он сарын порматын шалгалт
kable(df[1:10,]) %>%
  kable_styling(bootstrap_options = c("striped", "hover", "condensed")) %>% 
  column_spec(6, color = 'red', bold = T) %>% 
  scroll_box(width = "100%", height = "352px")

show_id	type	title	director	cast	country	date_added	release_year	rating	duration	listed_in
s1	Movie	Dick Johnson Is Dead	Kirsten Johnson	NA	United States	2021-09-25	2020	PG-13	90 min	Documentaries
s2	TV Show	Blood & Water	NA	Ama Qamata, Khosi Ngema, Gail Mabalane, Thabang Molaba, Dillon Windvogel, Natasha Thahane, Arno Greeff, Xolile Tshabalala, Getmore Sithole, Cindy Mahlangu, Ryle De Morny, Greteli Fincham, Sello Maake Ka-Ncube, Odwa Gwanya, Mekaila Mathys, Sandi Schultz, Duane Williams, Shamilla Miller, Patrick Mofokeng	South Africa	2021-09-24	2021	TV-MA	2 Seasons	International TV Shows, TV Dramas, TV Mysteries
s3	TV Show	Ganglands	Julien Leclercq	Sami Bouajila, Tracy Gotoas, Samuel Jouy, Nabiha Akkari, Sofia Lesaffre, Salim Kechiouche, Noureddine Farihi, Geert Van Rampelberg, Bakary Diombera	NA	2021-09-24	2021	TV-MA	1 Season	Crime TV Shows, International TV Shows, TV Action & Adventure
s4	TV Show	Jailbirds New Orleans	NA	NA	NA	2021-09-24	2021	TV-MA	1 Season	Docuseries, Reality TV
s5	TV Show	Kota Factory	NA	Mayur More, Jitendra Kumar, Ranjan Raj, Alam Khan, Ahsaas Channa, Revathi Pillai, Urvi Singh, Arun Kumar	India	2021-09-24	2021	TV-MA	2 Seasons	International TV Shows, Romantic TV Shows, TV Comedies
s6	TV Show	Midnight Mass	Mike Flanagan	Kate Siegel, Zach Gilford, Hamish Linklater, Henry Thomas, Kristin Lehman, Samantha Sloyan, Igby Rigney, Rahul Kohli, Annarah Cymone, Annabeth Gish, Alex Essoe, Rahul Abburi, Matt Biedel, Michael Trucco, Crystal Balint, Louis Oliver	NA	2021-09-24	2021	TV-MA	1 Season	TV Dramas, TV Horror, TV Mysteries
s7	Movie	My Little Pony: A New Generation	Robert Cullen, José Luis Ucha	Vanessa Hudgens, Kimiko Glenn, James Marsden, Sofia Carson, Liza Koshy, Ken Jeong, Elizabeth Perkins, Jane Krakowski, Michael McKean, Phil LaMarr	NA	2021-09-24	2021	PG	91 min	Children & Family Movies
s8	Movie	Sankofa	Haile Gerima	Kofi Ghanaba, Oyafunmike Ogunlano, Alexandra Duah, Nick Medley, Mutabaruka, Afemo Omilami, Reggie Carter, Mzuri	United States, Ghana, Burkina Faso, United Kingdom, Germany, Ethiopia	2021-09-24	1993	TV-MA	125 min	Dramas, Independent Movies, International Movies
s9	TV Show	The Great British Baking Show	Andy Devonshire	Mel Giedroyc, Sue Perkins, Mary Berry, Paul Hollywood	United Kingdom	2021-09-24	2021	TV-14	9 Seasons	British TV Shows, Reality TV
s10	Movie	The Starling	Theodore Melfi	Melissa McCarthy, Chris O'Dowd, Kevin Kline, Timothy Olyphant, Daveed Diggs, Skyler Gisondo, Laura Harrier, Rosalind Chao, Kimberly Quinn, Loretta Devine, Ravi Kapoor	United States	2021-09-24	2021	PG-13	104 min	Comedies, Dramas

4. Дүрслэх эцсийн алхамууд ба ойлголтууд

4.1 Агуулгын төрлөөр эзлэх хувь

content_by_type <- df %>% group_by(type) %>% 
  summarise(count = n())

plot_ly(content_by_type, labels = ~type, values = ~count, 
        type = 'pie', marker = list(colors = c("#bd3939", "#399ba3"))) %>% 
  layout(xaxis = list(showgrid = F, zeroline = F, showticklabels = F),
         yaxis = list(showgrid = F, zeroline = F, showticklabels = F),
         title = "Агуулгын төрлөөр эзлэх хувь", margin = list(t = 54),
         legend = list(x = 100, y = 0.5))

4.2 Үйлдвэрлэсэн агуулгын хэмжээгээр эхний 12 улс

s <- strsplit(df$country, split = ", ")
cntry_split <- data.frame(type = rep(df$type, sapply(s, length)), country = unlist(s))
cntry_split$country <- as.character(gsub(",","", cntry_split$country))

amount_by_country <- na.omit(cntry_split) %>%
  group_by(country, type) %>%
  summarise(count = n())

`summarise()` has grouped output by 'country'. You can override using the `.groups` argument.

w <- reshape(data = data.frame(amount_by_country), 
             idvar = "country",
             v.names = "count",
             timevar = "type",
             direction = "wide") %>% 
  arrange(desc(count.Movie)) %>% top_n(12)

Selecting by count.TV Show

names(w)[2] <- "count_movie"
names(w)[3] <- "count_tv_show"
w <- w[order(desc(w$count_movie + w$count_tv_show)),] 

plot_ly(w, x = w$country, y = ~count_movie, 
        type = 'bar', name = 'Movie', marker = list(color = '#bd3939')) %>% 
  add_trace(y = ~count_tv_show, name = 'TV Show', marker = list(color = '#399ba3')) %>% 
  layout(xaxis = list(categoryorder = "array", 
                      categoryarray = w$country, 
                      title = "Улс"), 
         yaxis = list(title = 'Өгөгдлийн тоо'),
         barmode = 'stack', 
         title = "Үйлдвэрлэсэн агуулгын хэмжээгээр эхний 12 улс", margin = list(t = 54),
         legend = list(x = 100, y = 0.5)) 

4.3 Жилийн болгоны агуулгын өсөлт

df_by_date_full <- df %>% group_by(date_added) %>% 
  summarise(added_today = n()) %>% 
  mutate(total_number_of_content = cumsum(added_today), type = "Total")

df_by_date <- df %>% group_by(date_added, type) %>% 
  summarise(added_today = n()) %>% 
  ungroup() %>% 
  group_by(type) %>%
  mutate(total_number_of_content = cumsum(added_today))

`summarise()` has grouped output by 'date_added'. You can override using the `.groups` argument.

full_data <- rbind(as.data.frame(df_by_date_full), as.data.frame(df_by_date))

plot_ly(full_data, x = ~date_added, y = ~total_number_of_content, 
        mode = 'lines', type = 'scatter',
        color = ~type, colors = c("#bd3939",  "#9addbd", "#399ba3")) %>% 
  layout(yaxis = list(title = 'Тоо'), 
         xaxis = list(title = 'он'), 
         title = "Жилийн болгоны агуулгын өсөлт", margin = list(t = 54),
         legend = list(x = 100, y = 0.5))

4.4 Сард нэмэгдсэн агуулгын хэмжээ

df_by_date_month <- df %>% group_by(month_added = floor_date(date_added, "month"), type) %>%
  summarise(added_today = n())

`summarise()` has grouped output by 'month_added'. You can override using the `.groups` argument.

wd <- reshape(data = data.frame(df_by_date_month),
              idvar = "month_added",
              v.names = "added_today",
              timevar = "type",
              direction = "wide")

names(wd)[2] <- "added_today_movie"
names(wd)[3] <- "added_today_tv_show"
wd$added_today_movie[is.na(wd$added_today_movie)] <- 0
wd$added_today_tv_show[is.na(wd$added_today_tv_show)] <- 0
wd <-na.omit(wd)

plot_ly(wd, x = wd$month_added, y = ~added_today_movie, 
        type = 'bar', name = 'Movie', 
        marker = list(color = '#bd3939')) %>% 
  add_trace(y = ~added_today_tv_show, 
            name = 'TV Show', 
            marker = list(color = '#399ba3')) %>% 
  layout(xaxis = list(categoryorder = 'array', 
                      categoryarray = wd$month_added, 
                      title = 'Он'), 
         yaxis = list(title = 'Тоо'), 
         barmode = 'stack', 
         title = "Сард нэмэгдсэн агуулгын хэмжээ", margin = list(t = 54),
         legend = list(x = 100, y = 0.5))

4.5 Үнэлгээгээр агуулгын хуваарилалт

df_by_rating <- df %>% group_by(rating) %>% 
  summarise(count = n())

plot_ly(df_by_rating, type = 'pie',
        labels = ~rating, values = ~count) %>% 
  layout(xaxis = list(showgrid = F, zeroline = F, showticklabels = F),
         yaxis = list(showgrid = F, zeroline = F, showticklabels = F),
         title = "Үнэлгээгээр агуулгын хуваарилалт", margin = list(t = 54),
         legend = list(x = 100, y = 0.5))

4.6 Шилдэг төрлүүд (Кино болон ТВ шоу)

s_genres <- strsplit(df$listed_in, split = ", ")
genres_listed_in <- data.frame(type = rep(df$type, sapply(s_genres, length)), 
                               listed_in = unlist(s_genres))
genres_listed_in$listed_in <- as.character(gsub(",","",genres_listed_in$listed_in))

df_by_listed_in <- genres_listed_in %>% 
  group_by(type, listed_in) %>% 
  summarise(count = n()) %>% 
  arrange(desc(count)) %>% top_n(10)

`summarise()` has grouped output by 'type'. You can override using the `.groups` argument.Selecting by count

plot_ly(df_by_listed_in, x = ~listed_in, y = ~count,
        type = 'bar', color = ~type,
        colors = c("#bd3939", "#399ba3")) %>%
  layout(xaxis = list(categoryorder = "array", 
                      categoryarray = df_by_listed_in$listed_in, 
                      title = 'Төрөл',
                      tickangle = 45), 
         yaxis = list(title = 'Тоо хэмжээ'), 
         title = "Шилдэг төрлүүд (Кино болон ТВ шоу)", margin = list(t = 54),
         legend = list(x = 100, y = 0.5))

4.7 Шилдэг 12 орны киноны үргэлжлэх хугацаа

mov_duration_cntry <- na.omit(df[df$type == "Movie",][,c("country", "duration")])

s_dur <- strsplit(mov_duration_cntry$country, split = ", ")
duration_full <- data.frame(duration = rep(mov_duration_cntry$duration,
                                           sapply(s_dur, length)),
                            country = unlist(s_dur))
duration_full$duration <- as.numeric(gsub(" min","", duration_full$duration))

duration_full_subset <- duration_full[duration_full$country %in% 
                                        c("United States", "India", "United Kingdom",
                                          "Canada", "France", "Japan", "Spain", "South Korea",
                                          "Mexico", "Australia", "China", "Taiwan"),]

plot_ly(duration_full_subset, y = ~duration, color = ~country, type = "box") %>% 
  layout(xaxis = list(title = "Улс"), 
         yaxis = list(title = 'Хугацаа (минутаар)'),
         title = "Шилдэг 12 орны киноны үргэлжлэх хугацаа", margin = list(t = 54),
         legend = list(x = 100, y = 0.5))

Warning: n too large, allowed maximum for palette Set2 is 8
Returning the palette you asked for with that many colors
Warning: n too large, allowed maximum for palette Set2 is 8
Returning the palette you asked for with that many colors
Warning: n too large, allowed maximum for palette Set2 is 8
Returning the palette you asked for with that many colors
Warning: n too large, allowed maximum for palette Set2 is 8
Returning the palette you asked for with that many colors

4.8 Ангилалуудыг харуулах: Корреляци ба хамгийн түгээмэл

df_show_categories <- df %>% 
                        select(c('show_id','type','listed_in')) %>% 
                        separate_rows(listed_in, sep = ',') %>%
                        rename(Show_Category = listed_in)
df_show_categories$Show_Category <- trimws(df_show_categories$Show_Category)
head(df_show_categories)

NA

df_show_categories %>% mutate(Show_Category = fct_infreq(Show_Category)) %>% 
        ggplot(aes(x = Show_Category)) + 
            geom_bar() + scale_x_discrete() + facet_wrap(~type, scales = 'free_x')  +  theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1)) + coord_cartesian(xlim = c(1,20))

df_unique_categories <- df_show_categories %>% group_by(type,Show_Category) %>%  summarise()

`summarise()` has grouped output by 'type'. You can override using the `.groups` argument.

df_category_correlations_movies <- data.frame(expand_grid(type = 'Movie', 
                                             Category1 = subset(df_unique_categories, type == 'Movie')$Show_Category,
                                             Category2 = subset(df_unique_categories, type == 'Movie')$Show_Category))
                                  
df_category_correlations_TV <-      data.frame(expand_grid(type = 'TV Show', 
                                             Category1 = subset(df_unique_categories, type == 'TV Show')$Show_Category,
                                             Category2 = subset(df_unique_categories, type == 'TV Show')$Show_Category))
                                 
df_category_correlations <- rbind(df_category_correlations_movies,df_category_correlations_TV)
df_category_correlations$matched_count <- apply(df_category_correlations, MARGIN = 1,FUN = function(x) {
                                            length(intersect(subset(df_show_categories, type == x['type'] & Show_Category == x['Category1'])$show_id,
                                            subset(df_show_categories, type == x['type'] & Show_Category == x['Category2'])$show_id))})

df_category_correlations <- subset(df_category_correlations, (as.character(Category1) < as.character(Category2)) & (matched_count > 0))
# Change plot size to 8 x 3
options(repr.plot.width=14, repr.plot.height=10)

ggplot(subset(df_category_correlations, type == 'Movie'), aes(x = Category1, y = Category2, fill = matched_count)) + 
  geom_tile() + facet_wrap( ~type, scales = 'free')  + scale_fill_distiller(palette = "Spectral") + 
            theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1), legend.text = element_text(size = 14), legend.title = element_text(size = 16))

ggplot(subset(df_category_correlations, type == 'TV Show'), aes(x = Category1, y = Category2, fill = matched_count)) + 
        geom_tile() + facet_wrap( ~type, scales = 'free') +  scale_fill_distiller(palette = "Spectral") + 
            theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1), , legend.text = element_text(size = 14), legend.title = element_text(size = 16))

4.9 Жүжигчидтэй холбоотой өгөгдөл

df %>% select(c('show_id','cast','director')) %>% 
        gather(key = 'role', value = 'person', cast, director) %>% 
             filter(person != "") %>% separate_rows(person, sep = ',') -> df_show_people

df_show_people$person <- trimws(df_show_people$person)
head(df_show_people)

df_people_freq<- df_show_people %>% group_by(person,role) %>% 
                    summarise(count = n()) %>% arrange(desc(count))

`summarise()` has grouped output by 'person'. You can override using the `.groups` argument.

df_people_freq %>% group_by(role) %>% top_n(10,count) %>% ungroup() %>% ggplot(aes(x = fct_reorder(person,count,.desc = T), y = count, fill = role)) + 
            geom_bar(stat = 'identity') + scale_x_discrete() + facet_wrap(~role, scales = 'free_x')  + theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1),legend.position = 'none') + labs(x = 'жүжигчин болон зохиолчдын нэрс')